© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 47832
    Prev
    Next
    INDEX
    Explanations

    bear followed by various nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     "...
    -2.83
    ⚣
    -2.44
    ..."
    -2.44
    และ
    -2.39
    ;"
    -2.38
     '
    -2.30
    beitung
    -2.30
    ベーション
    -2.28
    的で
    -2.27
    ឵
    -2.27
    POSITIVE LOGITS
    </i>
    3.48
     ‘‘
    2.97
    s
    2.39
    )」
    2.33
     are
    2.30
    or
    2.28
    ’,
    2.23
    </h3>
    2.16
    that
    2.16
    </blockquote>
    2.09
    Activations Density 0.007%

    No Known Activations